Search

Grain moisture content (GMC) is a key indicator of the appropriate harvest period of rice. Conventional testing is time-consuming and laborious, thus not to be implemented over vast areas and to enable the estimation of future changes for revealing optimal harvesting. Images of single panicles were shot with smartphones and corrected using a spectral–geometric correction board. In total, 86 panicle samples were obtained each time and then dried at 80 °C for 7 days to acquire the wet-basis GMC. In total, 517 valid samples were obtained, in which 80% was randomly used for training and 20% was used for testing to construct the image-based GMC assessment model. In total, 17 GMC surveys from a total of 201 samples were also performed from an area of 1 m2 representing on-site GMC, which enabled a multi-day GMC prediction. Eight color indices were selected using principal component analysis for building four machine learning models, including random forest, multilayer perceptron, support vector regression (SVR), and multivariate linear regression. The SVR model with a MAE of 1.23% was the most suitable for GMC of less than 40%. This study provides a real-time and cost-effective non-destructive GMC measurement using smartphones that enables on-farm prediction of harvest dates and facilitates the harvesting scheduling of agricultural machinery.

Cell phones and smart phones can be reconfigured as biomedical sensor devices but this requires specialized add-ons. In this paper we present a simple cell phone-based portable bioassay platform, which can be used with fluorescent assays in solution. The system consists of a tablet, a polarizer, a smart phone (camera) and a box that provides dark readout conditions. The assay in a well plate is placed on the tablet screen acting as an excitation source. A polarizer on top of the well plate separates excitation light from assay fluorescence emission enabling assay readout with a smartphone camera. The assay result is obtained by analysing the intensity of image pixels in an appropriate colour channel. With this device we carried out two assays, for collagenase and trypsin using fluorescein as the detected fluorophore. The results of collagenase assay with the lowest measured concentration of 3.75 µg/mL and 0.938 µg in total in the sample were comparable to those obtained by a microplate reader. The lowest measured amount of trypsin was 930 pg, which is comparable to the low detection limit of 400 pg for this assay obtained in a microplate reader. The device is sensitive enough to be used in point-of-care medical diagnostics of clinically relevant conditions, including arthritis, cystic fibrosis and acute pancreatitis.

The proliferation of mobile smart devices has led to a rapid increase of location-based services, many of which are amassing large datasets of user trajectory information. Unfortunately, current trajectory information is not yet sufficiently rich to support classification of user transportation modes. In this paper, we propose a method that employs both the Global Positioning System and accelerometer data from smart devices to classify user outdoor transportation modes. The classified modes include walking, bicycling, and motorized transport, in addition to the motionless (stationary) state, for which we provide new depth analysis. In our classification, stationary mode has two sub-modes: stay (remaining in the same place for a prolonged time period; e.g., in a parked vehicle) and wait (remaining at a location for a short period; e.g., waiting at a red traffic light). These two sub-modes present different semantics for data mining applications. We use support vector machines with parameters that are optimized for pattern recognition. In addition, we employ ant colony optimization to reduce the dimension of features and analyze their relative importance. The resulting classification system achieves an accuracy rate of 96.31% when applied to a dataset obtained from 18 mobile users.

In this paper, we review recent advances in on-chip sensors integrated with microfluidics for biological applications. Since the 1990s, much research has concentrated on developing a sensing system using optical phenomena such as surface plasmon resonance (SPR) and surface-enhanced Raman scattering (SERS) to improve the sensitivity of the device. The sensing performance can be significantly enhanced with the use of microfluidic chips to provide effective liquid manipulation and greater flexibility. We describe an optical image sensor with a simpler platform for better performance over a larger field of view (FOV) and greater depth of field (DOF). As a new trend, we review consumer electronics such as smart phones, tablets, Google glasses, etc. which are being incorporated in point-of-care (POC) testing systems. In addition, we discuss in detail the current optical sensing system integrated with a microfluidic chip.

Rich-sensor smart phones have made possible the recent birth of the mobile sensing research area as part of ubiquitous sensing which integrates other areas such as wireless sensor networks and web sensing. There are several types of mobile sensing: individual, participatory, opportunistic, crowd, social, etc. The object of sensing can be people-centered or environment-centered. The sensing domain can be home, urban, vehicular… Currently there are barriers that limit the social acceptance of mobile sensing systems. Examples of social barriers are privacy concerns, restrictive laws in some countries and the absence of economic incentives that might encourage people to participate in a sensing campaign. Several technical barriers are phone energy savings and the variety of sensors and software for their management. Some existing surveys partially tackle the topic of mobile sensing systems. Published papers theoretically or partially solve the above barriers. We complete the above surveys with new works, review the barriers of mobile sensing systems and propose some ideas for efficiently implementing sensing, fusion, learning, security, privacy and energy saving for any type of mobile sensing system, and propose several realistic research challenges. The main objective is to reduce the learning curve in mobile sensing systems where the complexity is very high.

Pedestrian dead reckoning (PDR) using smart phone-embedded micro-electro-mechanical system (MEMS) sensors plays a key role in ubiquitous localization indoors and outdoors. However, as a relative localization method, it suffers from the problem of error accumulation which prevents it from long term independent running. Heading estimation error is one of the main location error sources, and therefore, in order to improve the location tracking performance of the PDR method in complex environments, an approach based on robust adaptive Kalman filtering (RAKF) for estimating accurate headings is proposed. In our approach, outputs from gyroscope, accelerometer, and magnetometer sensors are fused using the solution of Kalman filtering (KF) that the heading measurements derived from accelerations and magnetic field data are used to correct the states integrated from angular rates. In order to identify and control measurement outliers, a maximum likelihood-type estimator (M-estimator)-based model is used. Moreover, an adaptive factor is applied to resist the negative effects of state model disturbances. Extensive experiments under static and dynamic conditions were conducted in indoor environments. The experimental results demonstrate the proposed approach provides more accurate heading estimates and supports more robust and dynamic adaptive location tracking, compared with methods based on conventional KF.

Thermal infrared imagery provides temperature information on target objects, and has been widely applied in non-destructive testing. However, thermal infrared imagery is not always able to display detailed textures of inspected objects, which hampers the understanding of geometric entities consisting of temperature information. Although some commercial software has been developed for 3D thermal model displays, the software requires the use of expensive specific thermal infrared sensors. This study proposes a cost-effective method for 3D thermal model reconstruction based on image-based modeling. Two smart phones and a low-cost thermal infrared camera are employed to acquire visible images and thermal images, respectively, that are fused for 3D thermal model reconstruction. The experiment results demonstrate that the proposed method is able to effectively reconstruct a 3D thermal model which extremely approximates its corresponding entity. The total computational time for the 3D thermal model reconstruction is intensive while generating dense points required for the creation of a geometric entity. Future work will improve the efficiency of the proposed method in order to expand its potential applications to in-time monitoring.

The use of a cell phone as a detection system is easy, simple and does not require trained personnel, which is in contrast to standard laboratory instruments. This paper deals with immobilization of acetylcholinesterase (AChE) in a gelatin matrix, and phenol red, as an indicator of AChE activity, is used in order to establish a method that is easily compatible with a camera device. AChE splits acetylcholine into choline and acetic acid, which changes the pH of a medium, resulting in a phenol red color change. The coloration changed in presence of an AChE inhibitor. Measurements were performed on 3D-printed, tube-shaped holder, and digital photography, with subsequent analysis of red-green-blue (RGB), served for assay purposes. Calibration of AChE inhibitors, tacrine and galantamine, was performed, with limit of detection equal to 1.1 nM and 1.28 µM, respectively. Interferences were also measured, resulting in a proof-of-method stability. The method was further successfully validated for the standard Ellman’s assay, and verified on murine plasma samples spiked with inhibitors.

This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user’s transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes.